网络在偷懒：理解图像去雨中的泛化问题
Networks are Slacking Off: Understanding Generalization Problem in Image Deraining
AI总结：
本文通过系统实验发现简化训练背景复杂度反而能提升图像去雨网络的泛化能力，揭示了网络在训练中倾向于学习最简单元素的“偷懒”机制，为低级视觉任务的泛化问题提供了新视角。
摘要：
深度去雨网络在实验室基准上表现成功，但在实际应用中部署时始终面临严重的泛化问题。深度学习领域的主流观点鼓励使用高度复杂的图像进行训练，期望更丰富的图像背景内容有助于克服泛化问题。然而，通过全面系统的实验，我们发现这一策略并未增强这些网络的泛化能力。相反，它加剧了网络对特定退化模式过拟合的倾向。我们的实验表明，通过简化训练背景图像的复杂度，可以获得更好的去雨网络泛化性能。这是因为网络在训练过程中“偷懒”，即学习图像背景和退化中最不复杂的元素以最小化训练损失。当背景图像比雨纹更简单时，网络会优先重建背景，从而抑制对雨纹模式的过拟合，并带来更好的泛化性能。我们的研究为更好地理解低级视觉任务中的泛化问题提供了有价值的视角和方法，并展示了实际应用的潜力。
英文摘要：
Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A prevailing perspective in deep learning encourages using highly complex data for training, with the expectation that richer image background content will facilitate overcoming the generalization problem. However, through comprehensive and systematic experimentation, we discover that this strategy does not enhance the generalization capability of these networks. On the contrary, it exacerbates the tendency of networks to overfit specific degradations. Our experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training background images. This is because that the networks are ``slacking off'' during training, that is, learning the least complex elements in the image background and degradation to minimize training loss. When the background images are less complex than the rain streaks, the network will prioritize the background reconstruction, thereby suppressing overfitting the rain patterns and leading to improved generalization performance. Our research offers a valuable perspective and methodology for better understanding the generalization problem in low-level vision tasks and displays promising potential for practical application.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
